agentleFS
florianbonnet14florianbonnet14/ThePowerOfAnalytics_ClaudeSkills/executive-summary-writer/SKILL.md

executive-summary-writer

Skill28 starsChanged 9 months agoMITView on GitHub

Transform analysis findings into clear, actionable executive summaries using the MAIN framework (Motive, Answer, Impact, Next steps) and Pyramidal Principle. Use when completing any analysis that needs stakeholder buy-in, preparing for leadership meetings, documenting investigation findings, writing business reviews, creating post-mortems, proposing initiatives based on data, or communicating insights to executives.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 10 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈10

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read and analyze the content

    line 20
  2. Distinctive:

    Create a clean document with:

    line 107
  3. Distinctive:

    Answer First: Always state findings and recommendations upfront, then support with context.

    line 115
  4. Distinctive:

    Quantify Everything: Use specific numbers with units.

    line 117
  5. Distinctive:

    Burying the lede: Don't save the answer for later.

    line 154
  6. Distinctive:

    No "So What?": Always explain implications and required actions

    line 158
  7. Distinctive:

    Be conversational: Ask one question at a time, don't overwhelm

    line 162
  8. Distinctive:

    Offer examples: If user is stuck, provide examples to clarify

    line 165
  9. Distinctive:

    Stay focused: Keep gathering info for MAIN, resist tangents

    line 166
  10. Distinctive:

    Validate completeness: Before drafting, confirm you have all pieces

    line 167

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Executive Summary Writer

Transform complex analysis into clear, actionable executive summaries that drive decision-making.

Workflow

Phase 1: Understand the Context

Ask the user:

"Do you have an analysis file that contains the context and results of your analysis?"

If YES:

  • Request the file
  • Read and analyze the content
  • Extract: business context, key findings, data/metrics, recommendations (if any)
  • Proceed to Phase 2 with extracted information

If NO:

  • Explain you'll gather information through questions
  • Proceed to Phase 2 with interactive questioning

Phase 2: Gather MAIN Components

Collect information for each component in order. If information was extracted from a file, confirm/clarify missing pieces. If no file, ask targeted questions:

M - Motive (2-4 sentences, 50-100 words)

Ask:

  • "What business problem or context triggered this analysis?"
  • "What recent changes or trends prompted this investigation?"
  • "Who is affected and what's at stake?"

Confirm you have:

  • Business context
  • Triggering event
  • Scope/focus

A - Answer (3-5 sentences, 75-125 words)

Ask:

  • "What did you find? (Main findings in 1-2 sentences)"
  • "What do you recommend should be done?"
  • "What outcome do you expect if this recommendation is followed?"

Validate with "So What?" test:

  • Can someone act on this without reading further?
  • Is it clear what success looks like?
  • Would a busy executive understand the takeaway?

I - Impact (3-5 sentences, 75-150 words)

Ask:

  • "What business metrics are affected? (revenue, users, costs)"
  • "What's the magnitude? (specific numbers)"
  • "What's the timeline for impact?"
  • "What happens if no action is taken?"

Ensure you have:

  • Quantified positive impact (with numbers and units)
  • Quantified negative impact/risk
  • Timeline and confidence level

N - Next Steps (3-7 items, 100-200 words)

Ask:

  • "What specific actions need to happen?"
  • "Who owns each action?"
  • "What are the timelines/ETAs?"
  • "How will success be measured?"

Each action must have:

  • Specific action (not vague)
  • Owner (name, not team)
  • ETA (date)
  • Success criteria

Phase 3: Draft & Review

  1. Generate the executive summary using the MAIN structure
  2. Present draft to user for review
  3. Iterate based on feedback

Phase 4: Quality Check

Before finalizing, verify:

Content Quality:

  • Answer appears in first 3 sentences
  • "So What?" is crystal clear
  • All impacts quantified with units ($, %, numbers)
  • Recommendations specific and actionable
  • Owners and dates assigned to all actions
  • Can be understood without further sections
  • Under 1 page for executive summary section

Writing Quality:

  • Active voice (not passive)
  • Short sentences and paragraphs
  • No jargon without explanation
  • Numbers formatted consistently
  • Specific numbers over vague terms ("40%" not "many")

Phase 5: Deliver

Create a clean document with:

  1. Executive Summary (MAIN format)
  2. Optional: Supporting sections if user requests them

Save to /mnt/user-data/outputs/executive-summary.md

Key Principles

Answer First: Always state findings and recommendations upfront, then support with context.

Quantify Everything: Use specific numbers with units. "15% drop (from 40% to 34%)" not "significant decrease."

Be Specific: "Design 3 new onboarding flows by Nov 30 - Owner: Jane" not "Improve onboarding."

Pass the "So What?" Test: Executive must understand what to do without reading further.

Keep It Brief: Executive summary = 1 page maximum. Details go in appendix.

Framework Reference

For detailed guidance on each MAIN component, see:

  • references/main-framework.md - Complete framework with examples
  • references/templates.md - Templates for different scenarios
  • references/examples.md - Good vs bad examples

Output Format

# [Topic] - Executive Summary

## Motive
[2-4 sentences on context and why this matters]

## Answer
[3-5 sentences: findings, recommendation, expected outcome]

## Impact
[3-5 sentences: quantified business implications]

## Next Steps
1. [Action] - Owner: [Name] - ETA: [Date] - Success: [Metric]
2. [Action] - Owner: [Name] - ETA: [Date] - Success: [Metric]
3. [Action] - Owner: [Name] - ETA: [Date] - Success: [Metric]

Common Pitfalls to Avoid

  • Burying the lede: Don't save the answer for later. State it upfront.
  • Vague recommendations: "Improve UX" → "Add 3-step interactive tutorial by Dec 15"
  • No quantification: "Big impact" → "$500K annual revenue at risk"
  • Too much detail upfront: Save detailed analysis for appendix
  • No "So What?": Always explain implications and required actions

User Interaction Guidelines

  • Be conversational: Ask one question at a time, don't overwhelm
  • Show progress: Let user know which component you're working on
  • Confirm understanding: Repeat back key points for validation
  • Offer examples: If user is stuck, provide examples to clarify
  • Stay focused: Keep gathering info for MAIN, resist tangents
  • Validate completeness: Before drafting, confirm you have all pieces

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.